© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 19708
    Prev
    Next
    INDEX
    Explanations

    phrases related to infinity and endlessness

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of infinity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewed
    -0.88
    nikov
    -0.88
    acus
    -0.82
    ington
    -0.81
    bourg
    -0.78
    neys
    -0.75
    iard
    -0.74
    iquette
    -0.72
    pillar
    -0.72
    roud
    -0.72
    POSITIVE LOGITS
     regress
    1.12
     Tsukuyomi
    0.91
     dimensional
    0.83
     amounts
    0.79
     amount
    0.79
     loops
    0.76
     gratification
    0.76
     repetition
    0.73
     quantities
    0.73
     postp
    0.70
    Activations Density 0.028%

    No Known Activations